Abstract: Technologies are provided for leveraging machine learning to predict the likelihood of near-future OUD for patients presenting in an emergency department. A model is trained with data corresponding to one or more of: gender, age, prior opioid use disorder diagnosis, prior opioid use disorder events, prior opioids, prior emergency department encounters, prior inpatient encounters, other medications, drug screening tests, hepatitis C tests, tobacco use questionnaires, prior results from medical tests, social history questionnaires, or other diagnoses to predict opioid use disorder risk for a population of patients. Upon receiving information available at an emergency department triage for a patient, the trained model is utilized to predict the opioid use disorder risk for the patient over a predetermined period of time.

Abstract: Analytics relevant to a particular patient are provided within the clinical decision workflow to provide data-driven decision support. When information is received from an end user device at a workflow service that indicates characteristics of a clinical decision support workflow being managed by the end user device for a patient, data is requested from one or more knowledge systems and electronic health record (EHR) data is requested from one or more EHRs. The data and the EHR data is aggregated within the clinical decision support workflow and a recommendation is provided to a clinician at a point of care via the end user device. For example, the recommendation may reveal that a particular care plan is, according to the aggregated data, the model recommendation.

Abstract: Analytics relevant to a particular patient are provided within the clinical decision workflow to provide data-driven decision support. When information is received from an end user device at a workflow service that indicates characteristics of a clinical decision support workflow being managed by the end user device for a patient, data is requested from one or more knowledge systems and electronic health record (EHR) data is requested from one or more EHRs. The data and the EHR data is aggregated within the clinical decision support workflow and a recommendation is provided to a clinician at a point of care via the end user device. For example, the recommendation may reveal that a particular care plan is, according to the aggregated data, the model recommendation.